Spoof detection by comparing images captured using visible-range and infrared (IR) illuminations

Patent metadata

Field	Value
Publication number	US-11328043-B2
Application number	US-201916355374-A
Country	US
Kind code	B2
Filing date	Mar 15, 2019
Priority date	Mar 15, 2019
Publication date	May 10, 2022
Grant date	May 10, 2022

Abstract

Technology described herein can be embodied in a method for preventing access to a secure system based on determining a captured image to be of an alternative representation of a live person. The method includes capturing a first image and a second image of a subject illuminated by electromagnetic radiation in a first and a second wavelength ranges, respectively. The method also includes extracting, from the first image, a first portion representative of a sclera region of the subject, and from the second image, a second portion representative of the same region. It is determined that each of the first portion and the second portion includes features representative of vasculature in the sclera region, and in response, the subject in the image is identified to be an alternative representation of a live person. Upon search identification, the method includes preventing access to the secure system.

First claim

What is claimed is:

1. A method for preventing access to a secure system based on determining a captured image to be of an alternative representation of a live person, the method comprising:
capturing, by one or more image acquisition devices, a first image of a subject illuminated by electromagnetic radiation in a first wavelength range;
capturing, by the one or more image acquisition devices, a second image of the subject illuminated by electromagnetic radiation in a second wavelength range different from the first wavelength range;
extracting, by one or more processing devices, from the first image, a first portion representative of a sclera region of the subject;
extracting, by the one or more processing devices from the second image, a second portion representative of the sclera region of the subject;
determining, by the one or more processing devices that each of the first portion and the second portion includes features representative of vasculature in the sclera region;
responsive to determining that each of the first portion of the first image and the second portion of the second image includes features representative of vasculature in the sclera region, identifying the subject in the first image to be an alternative representation of a live person; and
responsive to identifying the subject in the first image to be an alternative representation of a live person, preventing access to the secure system.

2. The method of claim 1 , wherein the first wavelength range includes the range of visible light in the electromagnetic spectrum.

3. The method of claim 2 , wherein the first wavelength range comprises wavelengths in a 400-700 nm range.

4. The method of claim 1 , wherein the second wavelength range includes the infrared (IR) portion of the electromagnetic spectrum.

5. The method of claim 4 , wherein the second wavelength range comprises wavelengths in a 700-1400 nm range.

6. The method of claim 1 , wherein determining that each of the first portion and the second portion includes features representative of vasculature in the sclera region comprises:
generating, for each of the first and second portions, a frequency domain representation; and
determining, from each of the frequency domain representations, that an amount of high frequency features in the corresponding portion satisfies a threshold condition.

7. The method of claim 1 , wherein determining that each of the first portion and the second portion includes features representative of vasculature in the sclera region comprises:
performing, on each of the first and second portions, an edge detection process; and
determining, based on outputs generated by the edge detection process, that each of the first and second portions includes a plurality of edges representative of the vasculature.

8. The method of claim 1 , further comprising:
determining that a third portion of a third image of a second subject includes features representative of vasculature in a sclera region of the second subject, and that a fourth portion of a fourth image of the second subject does not include features representative of vasculature in the sclera region of the second subject;
responsive to determining that the third portion includes features representative of vasculature in the sclera region, and that the fourth portion does not include features representative of vasculature in the sclera region of the second subject, identifying the second subject in the third and fourth images to be a live person; and
responsive to identifying the second subject in the third and fourth images to be a live person, initiating an authentication process for determining if the live person is authorized to access the secure system.

9. The method of claim 1 , wherein the alternative representation of a live person comprises a photograph of the live person printed on paper.

10. The method of claim 1 , wherein the secure system comprises a user-interface disposed in a kiosk.

11. A system comprising:
an image acquisition device configured to capture a first image and a second image of a subject, wherein the first and second images are captured under electromagnetic radiation of a first wavelength range and a second wavelength range, respectively; and
an image analysis engine comprising one or more processing devices, the image analysis engine configured to:
extract, from the first image, a first portion representative of a sclera region of the subject,
extract, from the second image, a second portion representative of the sclera region of the subject,
determine that each of the first portion and the second portion includes features representative of vasculature in the sclera region;
responsive to determining that each of the first portion and the second portion includes features representative of vasculature in the sclera region, identify the subject in the first image to be an alternative representation of a live person; and
responsive to identifying the subject in the first image to be an alternative representation of a live person, preventing access to a secure system.

12. The system of claim 11 , wherein preventing access to the secure system comprises generating a control signal for an authentication engine that controls access to the secure system.

13. The system of claim 11 , wherein the first wavelength range includes the range of visible light in the electromagnetic spectrum.

14. The system of claim 13 , wherein the first wavelength range comprises wavelengths in a 400-700 nm range.

15. The system of claim 11 , wherein the second wavelength range includes the infrared (IR) portion of the electromagnetic spectrum.

16. The system of claim 15 , wherein the second wavelength range comprises wavelengths in a 700-1400 nm range.

17. The system of claim 11 , wherein determining that each of the first portion and the second portion includes features representative of vasculature in the sclera region comprises:
generating, for each of the first and second portions, a frequency domain representation; and
determining, from each of the frequency domain representations, that an amount of high frequency features in the corresponding portion satisfies a threshold condition.

18. The system of claim 11 , wherein determining that each of the first portion and the second portion includes features representative of vasculature in the sclera region comprises:
performing, on each of the first and second portions, an edge detection process; and
determining, based on outputs generated by the edge detection process, that each of the first and second portions includes a plurality of edges representative of the vasculature.

19. The system of claim 11 , wherein the image analysis engine is configured to:
determine that a third portion of a third image of a second subject includes features representative of vasculature in a sclera region of the second subject, and that a fourth portion of a fourth image of the second subject does not include features representative of vasculature in the sclera region of the second subject;
responsive to determining that the third portion includes features representative of vasculature in the sclera region of the second subject, and that the fourth portion does not include features representative of vasculature in the sclera region, identify the second subject in the third and fourth images to be a live person; and
responsive to identifying the second subject in the third and fourth images to be a live person, initiate an authentication process for determining if the live pers

Assignees

• Advanced New Technologies Co Ltd

Inventors

• Joshi Yash
• Gottemukkula Vikas

Classifications

• G06V40/45

  Detection of the body part being alive · CPC title

• G06V40/14

  Vascular patterns · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G06V10/143

  Sensing or illuminating at different wavelengths · CPC title